End of training

README.md

@@ -10,7 +10,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper Small Hi - Sanchit Gandhi
+- name: Whisper Small Hi - akash_sharma_test
   results:
   - task:
       name: Automatic Speech Recognition
@@ -24,18 +24,18 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 145.88785046728972
+      value: 57.14285714285714
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Small Hi - Sanchit Gandhi
+# Whisper Small Hi - akash_sharma_test
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3160
-- Wer: 145.8879
+- Loss: 0.9139
+- Wer: 57.1429
 
 ## Model description
 
@@ -65,13 +65,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0           | 100.0 | 1000 | 1.1096          | 105.6075 |
-| 0.0           | 200.0 | 2000 | 1.2097          | 120.8411 |
-| 0.0           | 300.0 | 3000 | 1.2667          | 134.4237 |
-| 0.0           | 400.0 | 4000 | 1.3021          | 140.5919 |
-| 0.0           | 500.0 | 5000 | 1.3160          | 145.8879 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0112        | 20.0  | 1000 | 0.7359          | 61.0390 |
+| 0.0           | 40.0  | 2000 | 0.8434          | 57.1429 |
+| 0.0           | 60.0  | 3000 | 0.8839          | 57.1429 |
+| 0.0           | 80.0  | 4000 | 0.9055          | 57.1429 |
+| 0.0           | 100.0 | 5000 | 0.9139          | 57.1429 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ce34884475dfce0ce1f19f5ef9a7edea4ae5a13b96580af04c31a2f10f49af
+oid sha256:72c8833110b4130d5bae77357d8bd861b0991f968d5eb75146adc7f6114edb9e
 size 966995080